Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs indicating a future action

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating subjects or participants in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.71
     Associated
    -0.67
     Monteneg
    -0.66
     understatement
    -0.62
     Engineers
    -0.60
     overriding
    -0.60
     Vine
    -0.60
     implication
    -0.60
     Unreal
    -0.59
    quartered
    -0.59
    POSITIVE LOGITS
    've
    1.09
     arrived
    1.00
     became
    0.97
     realised
    0.95
    'd
    0.93
     began
    0.92
     realized
    0.92
     stopped
    0.90
     started
    0.89
     ceased
    0.89
    Act Density 0.144%

    No Known Activations